Aesthetic gradients ex1
from Stable Diffusion 1.4 / 1.5 Comparison
method: Aesthetic gradients
train data: /c3cats/Aesthetic Gradient ex1
results:
https://gyazo.com/7a659929a8317d390ef0d7186dff05af
0.0
https://gyazo.com/e9f260cacb982f68a3bd02ed17cb7dd8
0.00002
https://gyazo.com/7a749c845c28249943743ff754eba396
0.00005
https://gyazo.com/6630881de7ddd735c986d7e1adaef5f1
0.0001
https://gyazo.com/bd5371e9143ecce064783f66dc747612
0.0002
https://gyazo.com/f2bec659bea3044881d3f46b635577b5
0.0005
https://gyazo.com/94d4c248b2bab06ab08d51e79d43e937
0.0
https://gyazo.com/6847267e82bfaa45962dd50a3a3d01a8
0.00002
https://gyazo.com/07cf0b18bde11db7f3605d32abdf8a8f
0.00005
https://gyazo.com/79f2df4b6712666238bf8cfe6b4553e8
0.0001
https://gyazo.com/583a322a9d37c8d278399a136930a0c3
0.0002
https://gyazo.com/c2811992d38d8170049e233c24e26df8
---
This page is auto-translated from /nishio/Aesthetic gradients ex1 using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I'm very happy to spread my thought to non-Japanese readers.